Acknowledgement
이 논문은 연구 수행에 있어 2024년도 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원과(RS-2023-00277326) 정보통신기획평가원의 지원을받았으며 (No.2021-0-00528, 하드웨어 중심 신뢰계산기반과 분산 데이터보호박스를 위한 표준 프로토콜 개발), 2024년도 BK21 FOUR 정보기술 미래인재교육연구단, 반도체 공동연구소 지원의 결과물이다. 또한, 연구장비를 지원하고 공간을 제공한 서울대학교 컴퓨터연구소에 감사드린다.
References
- Lee, Eunsang, et al. "Low-complexity deep convolutional neural networks on fully homomorphic encryption using multiplexed parallel convolutions." International Conference on Machine Learning. PMLR, 2022.
- CHEON, Jung Hee, et.al. "Homomorphic encryption for arithmetic of approximate numbers", ASIACRYPT 2017, Hong Kong, China, December 3-7, 2017, p. 409-437.
- CHILLOTTI, et.al. "TFHE: fast fully homomorphic encryption over the torus", Journal of Cryptology, 2020, 33.1: 34-91. https://doi.org/10.1007/s00145-019-09319-x
- Ekman, Magnus. Learning deep learning: Theory and practice of neural networks, computer vision, natural language processing, and transformers using TensorFlow. Addison-Wesley Professional, 2021.
- Lou, Qian, and Lei Jiang. "She: A fast and accurate deep neural network for encrypted data." Advances in neural information processing systems 32 (2019).
- Nagel, Markus, et al. "A white paper on neural network quantization." arXiv preprint arXiv:2106.08295 (2021).
- Brutzkus, Alon, Ran Gilad-Bachrach, and Oren Elisha. "Low latency privacy preserving inference." International Conference on Machine Learning. PMLR, 2019.